Vertaile menetelmiä
Tarkastele valitsemiasi menetelmiä rinnakkain; eroavat rivit korostetaan.
| Monikielinen GRU× | Monikielinen LSTM× | |
|---|---|---|
| Tieteenala | Syväoppiminen | Syväoppiminen |
| Menetelmäperhe | Machine learning | Machine learning |
| Syntyvuosi≠ | 2014 (GRU); multilingual applications from ~2016 | 1997 (LSTM); multilingual NLP applications from ~2016 |
| Kehittäjä≠ | Cho, K. et al. (GRU); multilingual extension by NLP community | Hochreiter, S. & Schmidhuber, J. (LSTM base); multilingual application by the NLP community from ~2016 |
| Tyyppi≠ | Recurrent sequence model (multilingual) | Recurrent neural network (sequence model) |
| Alkuperäislähde≠ | Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. Proceedings of EMNLP 2014, 1724–1734. DOI ↗ | Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ |
| Rinnakkaisnimet | Multilingual GRU, cross-lingual GRU, multilingual gated recurrent unit, multi-language GRU | Multilingual LSTM, Cross-lingual LSTM, Multi-language LSTM, Multilingual Recurrent Network |
| Liittyvät≠ | 4 | 5 |
| Tiivistelmä≠ | A Multilingual GRU is a Gated Recurrent Unit network trained on text data spanning multiple languages, enabling sequential modeling of language-sensitive tasks such as sentiment analysis, named entity recognition, and machine translation across language boundaries without requiring separate models per language. | A Multilingual LSTM is a Long Short-Term Memory recurrent network trained or fine-tuned to process sequences in multiple languages, typically by sharing a single model across language-specific or joint subword embeddings. It captures long-range dependencies in text and is applied to multilingual classification, named entity recognition, sentiment analysis, and sequence labeling. |
| ScholarGateAineisto ↗ |
|
|